Fix task selection: reset() accepts task param, all 3 tasks verified

factory_env/env.py

@@ -28,6 +28,13 @@ class FactoryEnv(Environment[FactoryAction, FactoryObservation, FactoryState]):
         self.max_steps: int = self.config["max_steps"]
 
     def reset(self, seed: Optional[int] = None, episode_id: Optional[str] = None, **kwargs) -> FactoryObservation:
+        # Allow task to be overridden at reset time (e.g. from inference script)
+        task = kwargs.get("task", self.task)
+        if task != self.task and task in TASKS:
+            self.task = task
+            self.config = TASKS[task]
+            self.max_steps = self.config["max_steps"]
+
         use_seed = seed if seed is not None else self.seed
         self._rng = random.Random(use_seed)
         self.time = 0

inference.py

@@ -189,7 +189,7 @@ async def main() -> None:
     log_start(task=TASK_NAME, env=BENCHMARK, model=MODEL_NAME)
 
     try:
-        result = await env.reset()
+        result = await env.reset(task=TASK_NAME)
         obs = result.observation
         last_reward = 0.0
 

pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.backends.legacy:build"
+
+[project]
+name = "factory-env"
+version = "1.0.0"
+description = "Smart Factory Scheduling — OpenEnv RL Environment"
+requires-python = ">=3.11"
+dependencies = [
+    "pydantic>=2.0",
+    "openai>=1.0",
+    "anthropic>=0.90",
+    "gradio>=6.0",
+    "openenv-core>=0.2.3",
+    "fastapi>=0.100",
+    "uvicorn>=0.23",
+    "websockets>=12.0",
+    "httpx>=0.27",
+]